Quickstart

This quickstart walks you through building powerful Search with Mixedbread's Stores. You'll turn your files into a searchable knowledge base and explore it using natural language queries.

Pick the approach that fits your workflow: use our SDKs for seamless programmatic control and integration into your applications, or run everything directly in your terminal with the CLI for streamlined scripting and automation.

Using the SDK

Before you begin, make sure you have:

API Key: Get your API key from the API Keys page
SDK Installed: Install the Mixedbread SDK for your preferred language

Python

pip install mixedbread

TypeScript

npm install @mixedbread/sdk

Create a Store, upload your files, and search with natural language:

Store Workflow

from mixedbread import Mixedbread
from pathlib import Path

# Initialize the client
mxbai = Mixedbread(api_key="YOUR_API_KEY")

# Create a Store
store = mxbai.stores.create(name="my-knowledge-base")

# Upload and process your files (PDFs, images, docs, code)
file_result = mxbai.stores.files.upload_and_poll(
    store_identifier=store.id, file=Path("document.pdf")
)

# Search your data with natural language
results = mxbai.stores.search(
    query="What are the key features?",
    store_identifiers=[store.id],
    top_k=3,
)

# Display the results
for chunk in results.data:
    print(chunk)

Working with Metadata

Add metadata during upload to categorize files and filter during search:

Store Workflow with Metadata Filtering

from mixedbread import Mixedbread
from pathlib import Path

# Initialize the client
mxbai = Mixedbread(api_key="YOUR_API_KEY")

# Create a Store
store = mxbai.stores.create(name="my-knowledge-base")

# Upload files with metadata for better organization
file_result = mxbai.stores.files.upload_and_poll(
    store_identifier=store.id,
    file=Path("./document.pdf"),
    metadata={
        "category": "documentation",
        "department": "engineering",
        "tags": ["api", "tutorial"],
    },
)

# Search with metadata filtering to find specific content
results = mxbai.stores.search(
    query="What are the key features?",
    store_identifiers=[store.id],
    top_k=3,
    filters={"key": "category", "operator": "eq", "value": "documentation"},
)

# Display the filtered results
for chunk in results.data:
    print(chunk)

Use metadata to organize files by category, department, or any custom attribute, then search only the relevant subsets.

Using the CLI

Before you begin, make sure you have:

API Key: Get your API key from the API Keys page
CLI Installed: Install the Mixedbread CLI using your preferred package manager

npm install -g @mixedbread/cli

# Save your API key (one-time setup)
mxbai config keys add YOUR_API_KEY default

# Create a Store
mxbai store create "my-knowledge-base"

# Upload and process your files (PDFs, images, docs, code)
mxbai store upload "my-knowledge-base" ./documents/

# Search your data with natural language
mxbai store search "my-knowledge-base" "What are the key features?"

Quickstart

Using the SDK

Working with Metadata

Using the CLI

On this page